Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit

mlx-community/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit

This model mlx-community/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit was converted to MLX format from nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct using mlx-lm version 0.22.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)